Back to Projects
Actively ExploringResearch in Progress
Future Research Directions in Trustworthy AI
Trustworthy AIMulti-Agent SystemsAlignment
Currently studying theoretical bounds of Reinforcement Learning and Graph Neural Networks while preparing future research directions in trustworthy AI.
Research Motivation
As autonomous agents are deployed in increasingly critical environments, ensuring their decision-making is robust, interpretable, and aligned with human values is paramount.
Discussion
Future Work
Exploring neuro-symbolic AI to inject logical constraints into deep reinforcement learning pipelines.